Structured Gradient Guidance for Few-Shot Adaptation in Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Hongye, Wang, Yichen, Pan, Ray, Liu, Guiran, Zhu, Binrong, Zhang, Hanlu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915316114653184
author Zheng, Hongye
Wang, Yichen
Pan, Ray
Liu, Guiran
Zhu, Binrong
Zhang, Hanlu
author_facet Zheng, Hongye
Wang, Yichen
Pan, Ray
Liu, Guiran
Zhu, Binrong
Zhang, Hanlu
contents This paper presents a gradient-informed fine-tuning method for large language models under few-shot conditions. The goal is to enhance task adaptability and training stability when data is limited. The method builds on a base loss function and introduces two gradient-related regularization terms. The first enforces gradient direction consistency to guide parameter updates along task-relevant directions and prevent drift. The second controls gradient magnitude to avoid abnormal updates. Together, these components support a more efficient and stable optimization path. To further improve cross-task generalization, the method incorporates a gradient alignment mechanism. This mechanism measures the consistency between optimization directions of the source and target tasks. It enhances fine-tuning performance in multi-task and cross-domain scenarios. Across various natural language understanding tasks, the method outperforms existing fine-tuning strategies in average accuracy, gradient stability, and directional alignment. Empirical evaluations under different sample sizes and domain-specific tasks confirm the method's robustness and broad applicability in low-resource environments. In particular, the method shows clear advantages in controlling parameter update paths. The results demonstrate that a gradient-based fine-tuning framework can effectively leverage the representational power of large language models. It ensures training stability while reducing dependence on large volumes of labeled data.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00726
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Structured Gradient Guidance for Few-Shot Adaptation in Large Language Models
Zheng, Hongye
Wang, Yichen
Pan, Ray
Liu, Guiran
Zhu, Binrong
Zhang, Hanlu
Computation and Language
This paper presents a gradient-informed fine-tuning method for large language models under few-shot conditions. The goal is to enhance task adaptability and training stability when data is limited. The method builds on a base loss function and introduces two gradient-related regularization terms. The first enforces gradient direction consistency to guide parameter updates along task-relevant directions and prevent drift. The second controls gradient magnitude to avoid abnormal updates. Together, these components support a more efficient and stable optimization path. To further improve cross-task generalization, the method incorporates a gradient alignment mechanism. This mechanism measures the consistency between optimization directions of the source and target tasks. It enhances fine-tuning performance in multi-task and cross-domain scenarios. Across various natural language understanding tasks, the method outperforms existing fine-tuning strategies in average accuracy, gradient stability, and directional alignment. Empirical evaluations under different sample sizes and domain-specific tasks confirm the method's robustness and broad applicability in low-resource environments. In particular, the method shows clear advantages in controlling parameter update paths. The results demonstrate that a gradient-based fine-tuning framework can effectively leverage the representational power of large language models. It ensures training stability while reducing dependence on large volumes of labeled data.
title Structured Gradient Guidance for Few-Shot Adaptation in Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2506.00726